feat: add release utilities (#14)

* feat: port git information on setup from spaCy

add corresponding numpy licence
remove auto-generated git_info submodule

* feat: add tagging helper scripts

* feat: update about.py to include __title__ key

* feat: add a version key in setup.cfg

* feat: add automatic version extraction from cfg file

* fix: adapt release utilities to new _version file

* feat: get package name from setup.cfg

* build: add write_version_py to the setup procedure

* fix: version extraction in setup.py

* fix: underline in licenses/3rd_party_licenses.txt

Co-authored-by: Sofie Van Landeghem <[email protected]>

* build: remove git_info at build time

* chore: remove irrelevant 3rd party license

* fix: adapt code to check spaCy git commit

* fix: use weasel version and drop use of git commit for lockfile

* chore: change first version identifier

* feat: add check for deprecated spaCy env vars

* test: env var check

* fix: use optional instead of |

* feat: remove automatic build time __version__

* feat: remove version checking altogether

* feat: drop Py3.6 & 3.7 support

* ci: remove Py 3.6 & 3.7

* feat: remove multiple import since we're dropping Py3.7 support

---------

Co-authored-by: Sofie Van Landeghem <[email protected]>

.github/workflows/tests.yml

@@ -52,12 +52,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python_version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
-        include:
-          - os: windows-2019
-            python_version: "3.6"
-          - os: ubuntu-20.04
-            python_version: "3.6"
+        python_version: ["3.8", "3.9", "3.10", "3.11"]
     runs-on: ${{ matrix.os }}
 
     steps:

.gitignore

@@ -44,7 +44,6 @@ Pipfile.lock
 *.egg
 .eggs
 MANIFEST
-spacy/git_info.py
 
 # Temporary files
 *.~*

bin/get-package.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+
+set -e
+
+version=$(grep "name = " setup.cfg)
+version=${version/__title__ = }
+version=${version/\'/}
+version=${version/\'/}
+version=${version/\"/}
+version=${version/\"/}
+
+echo $version

bin/get-version.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+
+set -e
+
+version=$(grep "version = " setup.cfg)
+version=${version/version = }
+version=${version/\'/}
+version=${version/\'/}
+version=${version/\"/}
+version=${version/\"/}
+
+echo $version

bin/push-tag.sh

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+
+set -e
+
+# Insist repository is clean
+git diff-index --quiet HEAD
+
+git checkout $1
+git pull origin $1
+git push origin $1
+
+version=$(grep "version = " setup.cfg)
+version=${version/version = }
+version=${version/\'/}
+version=${version/\'/}
+version=${version/\"/}
+version=${version/\"/}
+git tag "v$version"
+git push origin "v$version"

setup.cfg

@@ -1,4 +1,6 @@
 [metadata]
+name = weasel
+version = 0.0.0
 description = Weasel: A small and easy workflow system
 url = https://github.com/explosion/weasel/
 author = Explosion
@@ -15,11 +17,10 @@ classifiers =
     Operating System :: MacOS :: MacOS X
     Operating System :: Microsoft :: Windows
     Programming Language :: Python :: 3
-    Programming Language :: Python :: 3.6
-    Programming Language :: Python :: 3.7
     Programming Language :: Python :: 3.8
     Programming Language :: Python :: 3.9
     Programming Language :: Python :: 3.10
+    Programming Language :: Python :: 3.11
     Topic :: Scientific/Engineering
 project_urls =
     Release notes = https://github.com/explosion/weasel/releases

setup.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 
+
 if __name__ == "__main__":
     from setuptools import find_packages, setup
 
-    setup(name="weasel", packages=find_packages())
+    setup(packages=find_packages())

weasel/about.py

@@ -1,3 +1,2 @@
-__version__ = "3.5.0"
 __projects__ = "https://github.com/explosion/projects"
 __projects_branch__ = "v3"

weasel/cli/remote_storage.py

@@ -8,12 +8,10 @@
 
 from wasabi import msg
 
-from .. import about
 from .._util import download_file, ensure_pathy, get_checksum, get_hash, make_tempdir
 from .._util import upload_file
 from ..errors import Errors
-from ..git_info import GIT_VERSION
-from ..util import ENV_VARS, check_bool_env_var, get_minor_version
+from ..util import check_spacy_env_vars
 
 if TYPE_CHECKING:
     from pathy import FluidPath
@@ -161,12 +159,9 @@ def get_command_hash(
     currently installed packages, whatever environment variables have been marked
     as relevant, and the command.
     """
-    if check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION):
-        spacy_v = GIT_VERSION
-    else:
-        spacy_v = str(get_minor_version(about.__version__) or "")
+    check_spacy_env_vars()
     dep_checksums = [get_checksum(dep) for dep in sorted(deps)]
-    hashes = [spacy_v, site_hash, env_hash] + dep_checksums
+    hashes = [site_hash, env_hash] + dep_checksums
     hashes.extend(cmd)
     creation_bytes = "".join(hashes).encode("utf8")
     return hashlib.md5(creation_bytes).hexdigest()

weasel/cli/run.py

@@ -8,13 +8,10 @@
 from wasabi import msg
 from wasabi.util import locale_escape
 
-from .. import about
 from .._util import COMMAND, PROJECT_FILE, PROJECT_LOCK, Arg, Opt, app, get_checksum
 from .._util import get_hash, load_project_config, parse_config_overrides
-from ..git_info import GIT_VERSION
-from ..util import ENV_VARS, SimpleFrozenDict, SimpleFrozenList, check_bool_env_var
-from ..util import is_cwd, is_minor_version_match, join_command, run_command
-from ..util import split_command, working_dir
+from ..util import SimpleFrozenDict, SimpleFrozenList, check_spacy_env_vars, is_cwd
+from ..util import join_command, run_command, split_command, working_dir
 
 
 @app.command(
@@ -102,10 +99,10 @@ def project_run(
                 err_help = "Maybe you forgot to run the 'project assets' command or a previous step?"
                 err_exits = 1 if not dry else None
                 msg.fail(err, err_help, exits=err_exits)
-        check_spacy_commit = check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION)
+        check_spacy_env_vars()
         with working_dir(project_dir) as current_dir:
             msg.divider(subcommand)
-            rerun = check_rerun(current_dir, cmd, check_spacy_commit=check_spacy_commit)
+            rerun = check_rerun(current_dir, cmd)
             if not rerun and not force:
                 msg.info(f"Skipping '{cmd['name']}': nothing changed")
             else:
@@ -223,9 +220,6 @@ def validate_subcommand(
 def check_rerun(
     project_dir: Path,
     command: Dict[str, Any],
-    *,
-    check_spacy_version: bool = True,
-    check_spacy_commit: bool = False,
 ) -> bool:
     """Check if a command should be rerun because its settings or inputs/outputs
     changed.
@@ -248,23 +242,11 @@ def check_rerun(
     # Always run commands with no outputs (otherwise they'd always be skipped)
     if not entry.get("outs", []):
         return True
-    # Always rerun if spaCy version or commit hash changed
-    spacy_v = entry.get("spacy_version")
-    commit = entry.get("spacy_git_version")
-    if check_spacy_version and not is_minor_version_match(spacy_v, about.__version__):
-        info = f"({spacy_v} in {PROJECT_LOCK}, {about.__version__} current)"
-        msg.info(f"Re-running '{command['name']}': spaCy minor version changed {info}")
-        return True
-    if check_spacy_commit and commit != GIT_VERSION:
-        info = f"({commit} in {PROJECT_LOCK}, {GIT_VERSION} current)"
-        msg.info(f"Re-running '{command['name']}': spaCy commit changed {info}")
-        return True
     # If the entry in the lockfile matches the lockfile entry that would be
     # generated from the current command, we don't rerun because it means that
     # all inputs/outputs, hashes and scripts are the same and nothing changed
     lock_entry = get_lock_entry(project_dir, command)
-    exclude = ["spacy_version", "spacy_git_version"]
-    return get_hash(lock_entry, exclude=exclude) != get_hash(entry, exclude=exclude)
+    return get_hash(lock_entry) != get_hash(entry)
 
 
 def update_lockfile(project_dir: Path, command: Dict[str, Any]) -> None:
@@ -303,8 +285,6 @@ def get_lock_entry(project_dir: Path, command: Dict[str, Any]) -> Dict[str, Any]
         "script": command["script"],
         "deps": deps,
         "outs": [*outs, *outs_nc],
-        "spacy_version": about.__version__,
-        "spacy_git_version": GIT_VERSION,
     }
 
 

weasel/schemas.py

@@ -3,7 +3,8 @@
 from collections import defaultdict
 from typing import Any, Dict, List, Optional, Type, Union
 
-from pydantic import BaseModel, Field, StrictStr, ValidationError, root_validator
+from pydantic import BaseModel, BaseSettings, Field, StrictStr, ValidationError
+from pydantic import root_validator
 from wasabi import msg
 
 
@@ -91,3 +92,20 @@ def check_legacy_keys(cls, obj: Dict[str, Any]) -> Dict[str, Any]:
                 "which is now deprecated. Weasel will not validate your version of spaCy.",
             )
         return obj
+
+
+class SpacyEnvVars(BaseSettings):
+    SPACY_CONFIG_OVERRIDES: Optional[str] = None
+    SPACY_PROJECT_USE_GIT_VERSION: Optional[bool] = None
+
+    def check(self):
+        if self.SPACY_CONFIG_OVERRIDES is not None:
+            msg.warn(
+                "You've set a `SPACY_CONFIG_OVERRIDES` environment variable, "
+                "which is now deprecated. Weasel will not use it."
+            )
+        if self.SPACY_PROJECT_USE_GIT_VERSION is not None:
+            msg.warn(
+                "You've set a `SPACY_PROJECT_USE_GIT_VERSION` environment variable, "
+                "which is now deprecated. Weasel will not use it."
+            )

weasel/tests/test_cli_app.py

@@ -1,3 +1,4 @@
+import os
 from pathlib import Path
 from typing import Any, Dict
 
@@ -96,10 +97,60 @@ def test_project_run(project_dir: Path):
     result = CliRunner().invoke(app, ["run", "create", str(project_dir)])
     assert result.exit_code == 0
     assert test_file.is_file()
+
+    assert (
+        "You've set a `SPACY_CONFIG_OVERRIDES` environment variable"
+        not in result.output
+    )
+    assert (
+        "You've set a `SPACY_PROJECT_USE_GIT_VERSION` environment variable"
+        not in result.output
+    )
+
+    os.environ["SPACY_CONFIG_OVERRIDES"] = "test"
+    os.environ["SPACY_PROJECT_USE_GIT_VERSION"] = "false"
+
     result = CliRunner().invoke(app, ["run", "ok", str(project_dir)])
     assert result.exit_code == 0
     assert "okokok" in result.stdout
 
+    assert "You've set a `SPACY_CONFIG_OVERRIDES` environment variable" in result.output
+    assert (
+        "You've set a `SPACY_PROJECT_USE_GIT_VERSION` environment variable"
+        in result.output
+    )
+
+
+def test_check_spacy_env_vars(project_dir: Path, monkeypatch: pytest.MonkeyPatch):
+    # make sure dry run works
+    project_dir / "abc.txt"
+
+    monkeypatch.delenv("SPACY_CONFIG_OVERRIDES")
+    monkeypatch.delenv("SPACY_PROJECT_USE_GIT_VERSION")
+
+    result = CliRunner().invoke(app, ["run", "--dry", "create", str(project_dir)])
+    assert result.exit_code == 0
+    assert (
+        "You've set a `SPACY_CONFIG_OVERRIDES` environment variable"
+        not in result.output
+    )
+    assert (
+        "You've set a `SPACY_PROJECT_USE_GIT_VERSION` environment variable"
+        not in result.output
+    )
+
+    monkeypatch.setenv("SPACY_CONFIG_OVERRIDES", "test")
+    monkeypatch.setenv("SPACY_PROJECT_USE_GIT_VERSION", "false")
+
+    result = CliRunner().invoke(app, ["run", "--dry", "create", str(project_dir)])
+    assert result.exit_code == 0
+
+    assert "You've set a `SPACY_CONFIG_OVERRIDES` environment variable" in result.output
+    assert (
+        "You've set a `SPACY_PROJECT_USE_GIT_VERSION` environment variable"
+        in result.output
+    )
+
 
 @pytest.mark.skipif(not has_git(), reason="git not installed")
 @pytest.mark.parametrize(

weasel/util.py

@@ -20,6 +20,7 @@
 
 from .compat import is_windows
 from .errors import Errors, Warnings
+from .schemas import SpacyEnvVars
 
 logger = logging.getLogger("spacy")
 logger_stream_handler = logging.StreamHandler()
@@ -30,8 +31,11 @@
 
 
 class ENV_VARS:
-    CONFIG_OVERRIDES = "SPACY_CONFIG_OVERRIDES"
-    PROJECT_USE_GIT_VERSION = "SPACY_PROJECT_USE_GIT_VERSION"
+    CONFIG_OVERRIDES = "WEASEL_CONFIG_OVERRIDES"
+
+
+def check_spacy_env_vars():
+    SpacyEnvVars().check()
 
 
 class SimpleFrozenDict(dict):